Hi all,
I was looking at some data trying to determine the degree of
overdispersion when I noticed that the point estimate and standard error
for a svy: nbreg and a svy: poisson with only the outcome variable were
the same. When I ran this without svy (i.e., nbreg and poisson) they
differed. Can someone tell me why the survey approach produces
identical results? Below, I have done this with a Stata dataset
(alq99_00) and got the same results.
Jason Ferris
AER Centre for Alcohol Policy Research
Turning Point Alcohol and Drug Centre
Victoria, Australia
Example:
* using stata-press dataset alq99_00
. webuse alq99_00, clear
. gen drinkdays=alq120q if alq120q<=365
(6451 missing values generated)
. svyset
pweight: wtmec2yr
VCE: linearized
Single unit: missing
Strata 1: sdmvstra
SU 1: sdmvpsu
FPC 1: <zero>
************
* weighted *
************
. svy: nbreg drinkdays
(running nbreg on estimation sample)
Survey: Negative binomial regression
Number of strata = 13 Number of obs =
3948
Number of PSUs = 27 Population size =
96361343
Design df =
14
F( 0, 14) =
.
Prob > F =
.
------------------------------------------------------------------------
------
| Linearized
drinkdays | Coef. Std. Err. t P>|t| [95% Conf.
Interval]
-------------+----------------------------------------------------------
------
_cons | 1.081066 .0578862 18.68 0.000 .9569123
1.205219
-------------+----------------------------------------------------------
------
/lnalpha | .2746654 .0887549 .084305
.4650257
-------------+----------------------------------------------------------
------
alpha | 1.31609 .1168095 1.087961
1.592055
------------------------------------------------------------------------
------
. svy: poisson drinkdays
(running poisson on estimation sample)
Survey: Poisson regression
Number of strata = 13 Number of obs =
3948
Number of PSUs = 27 Population size =
96361343
Design df =
14
F( 0, 14) =
.
Prob > F =
.
------------------------------------------------------------------------
------
| Linearized
drinkdays | Coef. Std. Err. t P>|t| [95% Conf.
Interval]
-------------+----------------------------------------------------------
------
_cons | 1.081066 .0578862 18.68 0.000 .9569123
1.205219
------------------------------------------------------------------------
------
**************
* unweighted *
**************
. nbreg drinkdays, nolog
Negative binomial regression Number of obs =
3514
LR chi2(0) =
0.00
Dispersion = mean Prob > chi2 =
.
Log likelihood = -8053.3652 Pseudo R2 =
0.0000
------------------------------------------------------------------------
------
drinkdays | Coef. Std. Err. z P>|z| [95% Conf.
Interval]
-------------+----------------------------------------------------------
------
_cons | 1.19019 .0232271 51.24 0.000 1.144666
1.235714
-------------+----------------------------------------------------------
------
/lnalpha | .4647593 .029011 .4078988
.5216197
-------------+----------------------------------------------------------
------
alpha | 1.591631 .0461748 1.503655
1.684754
------------------------------------------------------------------------
------
Likelihood-ratio test of alpha=0: chibar2(01) = 2.0e+04 Prob>=chibar2 =
0.000
. poisson drinkdays, nolog
Poisson regression Number of obs =
3514
LR chi2(0) =
0.00
Prob > chi2 =
.
Log likelihood = -18257.672 Pseudo R2 =
0.0000
------------------------------------------------------------------------
------
drinkdays | Coef. Std. Err. z P>|z| [95% Conf.
Interval]
-------------+----------------------------------------------------------
------
_cons | 1.19019 .0093036 127.93 0.000 1.171955
1.208425
------------------------------------------------------------------------
------
------------------------------------------
DISCLAIMER: This message (including any attachments) is intended solely for the addressee(s) named and may contain confidential or privileged information.
If you are not the intended recipient, please delete it and notify the sender.
Views expressed in this message are those of the individual sender,and are not necessarily the views of the Turning Point Alcohol and Drug Centre Inc (ABN: 17 302 055 629).
<a href="http://www.turningpoint.org.au";>Turning Point Alcohol and Drug Centre Inc</a>
Although this message and any attachments have been scanned for viruses by 'Trend Micro InterScan' at the time of sending,
you are advised to rescan on receipt.
The whole or parts of this email may be subject to copyright of Turning Point Alcohol and Drug Centre Inc (ABN: 17 302 055 629), and/or third parties.
You can only re-transmit, distribute or use the material if you are authorised to do so.
Please consider the environment before printing this email or attachments.
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
